{ "openapi": "3.0.1", "info": { "title": "Site to Markdown Crawler: Website Content Crawler Alternative", "description": "Crawls a website into Markdown for AI and RAG use. Plain HTTP, 512 MB default allocation. Set page attempts in input and spend limits in Apify run options.", "version": "0.5", "x-build-id": "DDuJYTctRFsC9Gdbn" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/madrasco~site-markdown-crawler/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-madrasco-site-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/madrasco~site-markdown-crawler/runs": { "post": { "operationId": "runs-sync-madrasco-site-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/madrasco~site-markdown-crawler/run-sync": { "post": { "operationId": "run-sync-madrasco-site-markdown-crawler", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } } }, "components": { "schemas": { "inputSchema": { "type": "object", "properties": { "startUrls": { "title": "Start URLs", "minItems": 1, "type": "array", "description": "One or more URLs to start crawling from. Check the terms of every target site first, including linked subdomains and page-redirect destinations. Default discovery follows links on start domains and their subdomains and uses permitted sitemap URLs. The request queue deduplicates URLs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL of a web page", "format": "uri" } } } }, "maxPages": { "title": "Maximum pages", "minimum": 1, "maximum": 50000, "type": "integer", "description": "Limit page attempts and dataset rows, including free error, blocked, robots-disallowed, no-content and spend-skipped results. Enter 1 to 50,000. Default: 500. The runtime falls back to 500 for 0 only when schema validation is bypassed.", "default": 500 }, "maxTotalChargeUsd": { "title": "Spend cap (USD)", "minimum": 0, "type": "number", "description": "Legacy input field: this value does not set the platform spend cap. Set the maximum total charge in Apify run options for pay-per-event runs.", "default": 5 }, "sameDomainOnly": { "title": "Stay on the same domain", "type": "boolean", "description": "When true, follow links on the start domains and their subdomains. Keep true for link discovery. When false, only start URLs and sitemap URLs are crawled; links are not discovered.", "default": true }, "useSitemap": { "title": "Use sitemap", "type": "boolean", "description": "Seed the URL queue from permitted sitemap files advertised in robots.txt or at /sitemap.xml. Sitemap resources, indexes and sitemap redirects must stay on the start URL's exact scheme, host and port; robots rules and crawl-delay pacing apply. Disabling sitemap discovery still checks robots for pages.", "default": true }, "timeoutSecs": { "title": "Timeout per page (seconds)", "minimum": 3, "maximum": 60, "type": "integer", "description": "HTTP socket timeout in seconds. A complete page attempt can take longer because robots fetching, crawl-delay waits, redirects and parsing add time. Set the whole-run timeout separately in Apify run options.", "default": 20 }, "maxConcurrency": { "title": "Parallel requests", "minimum": 1, "maximum": 20, "type": "integer", "description": "How many page attempts to fetch and parse at once. Default: 2. Default memory allocation: 512 MB; selectable minimum: 256 MB. Higher concurrency can increase memory use.", "default": 2 } } }, "runsResponseSchema": { "type": "object", "properties": { "data": { "type": "object", "properties": { "id": { "type": "string" }, "actId": { "type": "string" }, "userId": { "type": "string" }, "startedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "finishedAt": { "type": "string", "format": "date-time", "example": "2025-01-08T00:00:00.000Z" }, "status": { "type": "string", "example": "READY" }, "meta": { "type": "object", "properties": { "origin": { "type": "string", "example": "API" }, "userAgent": { "type": "string" } } }, "stats": { "type": "object", "properties": { "inputBodyLen": { "type": "integer", "example": 2000 }, "rebootCount": { "type": "integer", "example": 0 }, "restartCount": { "type": "integer", "example": 0 }, "resurrectCount": { "type": "integer", "example": 0 }, "computeUnits": { "type": "integer", "example": 0 } } }, "options": { "type": "object", "properties": { "build": { "type": "string", "example": "latest" }, "timeoutSecs": { "type": "integer", "example": 300 }, "memoryMbytes": { "type": "integer", "example": 1024 }, "diskMbytes": { "type": "integer", "example": 2048 } } }, "buildId": { "type": "string" }, "defaultKeyValueStoreId": { "type": "string" }, "defaultDatasetId": { "type": "string" }, "defaultRequestQueueId": { "type": "string" }, "buildNumber": { "type": "string", "example": "1.0.0" }, "containerUrl": { "type": "string" }, "usage": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "integer", "example": 1 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } }, "usageTotalUsd": { "type": "number", "example": 0.00005 }, "usageUsd": { "type": "object", "properties": { "ACTOR_COMPUTE_UNITS": { "type": "integer", "example": 0 }, "DATASET_READS": { "type": "integer", "example": 0 }, "DATASET_WRITES": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_READS": { "type": "integer", "example": 0 }, "KEY_VALUE_STORE_WRITES": { "type": "number", "example": 0.00005 }, "KEY_VALUE_STORE_LISTS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_READS": { "type": "integer", "example": 0 }, "REQUEST_QUEUE_WRITES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_INTERNAL_GBYTES": { "type": "integer", "example": 0 }, "DATA_TRANSFER_EXTERNAL_GBYTES": { "type": "integer", "example": 0 }, "PROXY_RESIDENTIAL_TRANSFER_GBYTES": { "type": "integer", "example": 0 }, "PROXY_SERPS": { "type": "integer", "example": 0 }, "PROXY_UNBLOCKER_UNITS": { "type": "integer", "example": 0 } } } } } } } } } }